Evaluation of Multicomputers for Imaging Processing covers the proceedings of the 1984 Tanque Verde Workshop, held in Tucson. This book is organized into four parts encompassing 17 chapters that summarize the benchmark evaluation efforts specific to multicomputer systems designed for the efficient execution of image processing tasks. The first part considers the basic problem of benchmarking and presents an evaluation procedure or sets of instructions for establishing benchmark routines, tasks, and procedures. The next part deals with the simulation and evaluation. This part first examines semiconductor chips designed for use in imaging processing followed by the presentation of formulas for measuring algorithms, architecture efficiency, speedup, and processing element utilization for SIMD/MIMD multicomputers. This part also considers the image processing systems composed of various types of networks of processing elements. The third part describes a content-addressable array and its applications to machine vision, as well as the architecture and programming methods of the WARP multicomputer. This part further looks into the elevation measurements techniques by registering stereo pairs obtained from aerial photography using ""pass point"" correlation methods. The concluding part highlights the hardware implementations of general-purpose image processing systems with associated performance evaluations. Computer scientists and engineers will greatly benefit from this book.

Multicomputer Vision is a collection of papers and discussions presented at the 8th Workshop on Multicomputers, held in Rome, Italy on June 2-5, 1987. Contributors present multicomputer algorithms for image processing, evaluation and suggestions on multicomputer systems, and new designs in advanced architectures for computer vision. Separating 12 papers into chapters, this book first describes a pyramidal algorithm for image segmentation based on the definition of the "bimean of a population. It then examines the use of Polymorphic Torus architecture to yield positive results in the computation of Hough Transform through executing mesh and tree algorithms. The succeeding papers present the five-level quad-tree pyramid algorithm based on chips from the MPP machine and the algorithm databases required for scheduling and reconfiguration decisions based on the user's task definition. Other chapters oriented towards the evaluation of multicomputer systems are also provided. These chapters include discussions on multi-processor architectures based on perceptual tasks, the advantages of fine grain associative string structure for general purpose computer vision system, and the use of identical single processor elements for comparison between processor arrays and pipeline computers. The book also contains papers oriented on the design features of new multiprocessor architectures. These papers discuss the memory limitations of parallel machines and the physical realization of a one-dimensional array of 128 to 1024 identical processors. This book provides an informal frame of reference to researchers who are interested in the design and development of algorithms, and architectures or languages of multiprocessor systems.

Multicomputers and Image Processing: Algorithms and Programs is the second of a set presenting papers from the third meeting held in Madison, Wisconsin on May 27-30, 1981. The workshop explores the large and powerful multicomputer arrays and networks, with particular emphasis on the related aspects of developing algorithms and programs for multicomputer architectures. Separating 33 papers into chapters, this book reflects the three major aspects of the problem: user algorithms and programs; higher level languages; and multicomputer architectures. The first chapters present specific, larger structure, as well as whole program algorithms and their respective applications. Other chapters describe the important high-level programming of Fortran-based language for the massively parallel processors and the set-theory-based language for expressing the structural image processing and perceptual operations effected by Cytocomputer and other cellular-array-motivated architectures. The concluding chapters examine several major types of computer architectures that are being developed for large parallel-serial multicomputer systems. This book is of great value to computer programmers and scientists.

This book results from a Workshop on Multiresolution Image Processing and Analysis, held in Leesburg, VA on July 19-21, 1982. It contains updated ver sions of most of the papers that were presented at the Workshop, as well as new material added by the authors. Four of the presented papers were not available for inclusion in the book: D. Sabbah, A computing with connections approach to visual recognition; R. M. Haralick, Fitting the gray tone intensity surface as a function of neighborhood size; E. M. Riseman, Hierarchical boundary formation; and W. L. Mahaffey, L. S. Davis, and J. K. Aggarwal, Region correspondence in multi-resolution images taken from dynamic scenes. The number and variety of papers indicates the timeliness of the H0rkshop. Multiresolution methods are rapidly gaining recognition as an important theme in image processing and analysis. I would like to express my thanks to the National Science Foundation for their support of the Workshop under Grant MCS-82-05942; to Barbara Hope for organizing and administering the Workshop; to Janet Salzman and Fran Cohen, for retyping the papers; and above all, to the speakers and other partici pants, for making the Workshop possible.

This book contains the proceedings of the NATO Advanced Research Workshop held in Maratea (Italy), May 5-9, 1986 on Pyramidal Systems for Image Processing and Computer Vision. We had 40 participants from 11 countries playing an active part in the workshop and all the leaders of groups that have produced a prototype pyramid machine or a design for such a machine were present. Within the wide field of parallel architectures for image processing a new area was recently born and is growing healthily: the area of pyramidally structured multiprocessing systems. Essentially, the processors are arranged in planes (from a base to an apex) each one of which is generally a reduced (usually by a power of two) version of the plane underneath: these processors are horizontally interconnected (within a plane) and vertically connected with "fathers" (on top planes) and "children" on the plane below. This arrangement has a number of interesting features, all of which were amply discussed in our Workshop including the cellular array and hypercube versions of pyramids. A number of projects (in different parts of the world) are reported as well as some interesting applications in computer vision, tactile systems and numerical calculations.